diff options
Diffstat (limited to 'block')
-rw-r--r-- | block/Makefile | 2 | ||||
-rw-r--r-- | block/bdev.c | 1058 | ||||
-rw-r--r-- | block/bfq-cgroup.c | 6 | ||||
-rw-r--r-- | block/bfq-iosched.c | 16 | ||||
-rw-r--r-- | block/bio.c | 2 | ||||
-rw-r--r-- | block/blk-cgroup.c | 23 | ||||
-rw-r--r-- | block/blk-core.c | 148 | ||||
-rw-r--r-- | block/blk-integrity.c | 9 | ||||
-rw-r--r-- | block/blk-mq-debugfs.c | 1 | ||||
-rw-r--r-- | block/blk-mq-tag.c | 2 | ||||
-rw-r--r-- | block/blk-mq.c | 36 | ||||
-rw-r--r-- | block/blk-settings.c | 20 | ||||
-rw-r--r-- | block/blk-throttle.c | 1 | ||||
-rw-r--r-- | block/blk.h | 4 | ||||
-rw-r--r-- | block/bsg.c | 23 | ||||
-rw-r--r-- | block/fops.c | 639 | ||||
-rw-r--r-- | block/genhd.c | 35 | ||||
-rw-r--r-- | block/kyber-iosched.c | 10 | ||||
-rw-r--r-- | block/partitions/core.c | 1 |
19 files changed, 1922 insertions, 114 deletions
diff --git a/block/Makefile b/block/Makefile index 6cf40276d3cf..41aa1ba69c90 100644 --- a/block/Makefile +++ b/block/Makefile @@ -3,7 +3,7 @@ # Makefile for the kernel block layer # -obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \ +obj-$(CONFIG_BLOCK) := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \ blk-flush.o blk-settings.o blk-ioc.o blk-map.o \ blk-exec.o blk-merge.o blk-timeout.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ diff --git a/block/bdev.c b/block/bdev.c new file mode 100644 index 000000000000..485a258b0ab3 --- /dev/null +++ b/block/bdev.c @@ -0,0 +1,1058 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE + * Copyright (C) 2016 - 2020 Christoph Hellwig + */ + +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/kmod.h> +#include <linux/major.h> +#include <linux/device_cgroup.h> +#include <linux/blkdev.h> +#include <linux/backing-dev.h> +#include <linux/module.h> +#include <linux/blkpg.h> +#include <linux/magic.h> +#include <linux/buffer_head.h> +#include <linux/swap.h> +#include <linux/writeback.h> +#include <linux/mount.h> +#include <linux/pseudo_fs.h> +#include <linux/uio.h> +#include <linux/namei.h> +#include <linux/cleancache.h> +#include <linux/part_stat.h> +#include <linux/uaccess.h> +#include "../fs/internal.h" +#include "blk.h" + +struct bdev_inode { + struct block_device bdev; + struct inode vfs_inode; +}; + +static inline struct bdev_inode *BDEV_I(struct inode *inode) +{ + return container_of(inode, struct bdev_inode, vfs_inode); +} + +struct block_device *I_BDEV(struct inode *inode) +{ + return &BDEV_I(inode)->bdev; +} +EXPORT_SYMBOL(I_BDEV); + +static void bdev_write_inode(struct block_device *bdev) +{ + struct inode *inode = bdev->bd_inode; + int ret; + + spin_lock(&inode->i_lock); + while (inode->i_state & I_DIRTY) { + spin_unlock(&inode->i_lock); + ret = write_inode_now(inode, true); + if (ret) { + char name[BDEVNAME_SIZE]; + pr_warn_ratelimited("VFS: Dirty inode writeback failed " + "for block device %s (err=%d).\n", + bdevname(bdev, name), ret); + } + spin_lock(&inode->i_lock); + } + spin_unlock(&inode->i_lock); +} + +/* Kill _all_ buffers and pagecache , dirty or not.. */ +static void kill_bdev(struct block_device *bdev) +{ + struct address_space *mapping = bdev->bd_inode->i_mapping; + + if (mapping_empty(mapping)) + return; + + invalidate_bh_lrus(); + truncate_inode_pages(mapping, 0); +} + +/* Invalidate clean unused buffers and pagecache. */ +void invalidate_bdev(struct block_device *bdev) +{ + struct address_space *mapping = bdev->bd_inode->i_mapping; + + if (mapping->nrpages) { + invalidate_bh_lrus(); + lru_add_drain_all(); /* make sure all lru add caches are flushed */ + invalidate_mapping_pages(mapping, 0, -1); + } + /* 99% of the time, we don't need to flush the cleancache on the bdev. + * But, for the strange corners, lets be cautious + */ + cleancache_invalidate_inode(mapping); +} +EXPORT_SYMBOL(invalidate_bdev); + +/* + * Drop all buffers & page cache for given bdev range. This function bails + * with error if bdev has other exclusive owner (such as filesystem). + */ +int truncate_bdev_range(struct block_device *bdev, fmode_t mode, + loff_t lstart, loff_t lend) +{ + /* + * If we don't hold exclusive handle for the device, upgrade to it + * while we discard the buffer cache to avoid discarding buffers + * under live filesystem. + */ + if (!(mode & FMODE_EXCL)) { + int err = bd_prepare_to_claim(bdev, truncate_bdev_range); + if (err) + goto invalidate; + } + + truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend); + if (!(mode & FMODE_EXCL)) + bd_abort_claiming(bdev, truncate_bdev_range); + return 0; + +invalidate: + /* + * Someone else has handle exclusively open. Try invalidating instead. + * The 'end' argument is inclusive so the rounding is safe. + */ + return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping, + lstart >> PAGE_SHIFT, + lend >> PAGE_SHIFT); +} + +static void set_init_blocksize(struct block_device *bdev) +{ + unsigned int bsize = bdev_logical_block_size(bdev); + loff_t size = i_size_read(bdev->bd_inode); + + while (bsize < PAGE_SIZE) { + if (size & bsize) + break; + bsize <<= 1; + } + bdev->bd_inode->i_blkbits = blksize_bits(bsize); +} + +int set_blocksize(struct block_device *bdev, int size) +{ + /* Size must be a power of two, and between 512 and PAGE_SIZE */ + if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) + return -EINVAL; + + /* Size cannot be smaller than the size supported by the device */ + if (size < bdev_logical_block_size(bdev)) + return -EINVAL; + + /* Don't change the size if it is same as current */ + if (bdev->bd_inode->i_blkbits != blksize_bits(size)) { + sync_blockdev(bdev); + bdev->bd_inode->i_blkbits = blksize_bits(size); + kill_bdev(bdev); + } + return 0; +} + +EXPORT_SYMBOL(set_blocksize); + +int sb_set_blocksize(struct super_block *sb, int size) +{ + if (set_blocksize(sb->s_bdev, size)) + return 0; + /* If we get here, we know size is power of two + * and it's value is between 512 and PAGE_SIZE */ + sb->s_blocksize = size; + sb->s_blocksize_bits = blksize_bits(size); + return sb->s_blocksize; +} + +EXPORT_SYMBOL(sb_set_blocksize); + +int sb_min_blocksize(struct super_block *sb, int size) +{ + int minsize = bdev_logical_block_size(sb->s_bdev); + if (size < minsize) + size = minsize; + return sb_set_blocksize(sb, size); +} + +EXPORT_SYMBOL(sb_min_blocksize); + +int __sync_blockdev(struct block_device *bdev, int wait) +{ + if (!bdev) + return 0; + if (!wait) + return filemap_flush(bdev->bd_inode->i_mapping); + return filemap_write_and_wait(bdev->bd_inode->i_mapping); +} + +/* + * Write out and wait upon all the dirty data associated with a block + * device via its mapping. Does not take the superblock lock. + */ +int sync_blockdev(struct block_device *bdev) +{ + return __sync_blockdev(bdev, 1); +} +EXPORT_SYMBOL(sync_blockdev); + +/* + * Write out and wait upon all dirty data associated with this + * device. Filesystem data as well as the underlying block + * device. Takes the superblock lock. + */ +int fsync_bdev(struct block_device *bdev) +{ + struct super_block *sb = get_super(bdev); + if (sb) { + int res = sync_filesystem(sb); + drop_super(sb); + return res; + } + return sync_blockdev(bdev); +} +EXPORT_SYMBOL(fsync_bdev); + +/** + * freeze_bdev -- lock a filesystem and force it into a consistent state + * @bdev: blockdevice to lock + * + * If a superblock is found on this device, we take the s_umount semaphore + * on it to make sure nobody unmounts until the snapshot creation is done. + * The reference counter (bd_fsfreeze_count) guarantees that only the last + * unfreeze process can unfreeze the frozen filesystem actually when multiple + * freeze requests arrive simultaneously. It counts up in freeze_bdev() and + * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze + * actually. + */ +int freeze_bdev(struct block_device *bdev) +{ + struct super_block *sb; + int error = 0; + + mutex_lock(&bdev->bd_fsfreeze_mutex); + if (++bdev->bd_fsfreeze_count > 1) + goto done; + + sb = get_active_super(bdev); + if (!sb) + goto sync; + if (sb->s_op->freeze_super) + error = sb->s_op->freeze_super(sb); + else + error = freeze_super(sb); + deactivate_super(sb); + + if (error) { + bdev->bd_fsfreeze_count--; + goto done; + } + bdev->bd_fsfreeze_sb = sb; + +sync: + sync_blockdev(bdev); +done: + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return error; +} +EXPORT_SYMBOL(freeze_bdev); + +/** + * thaw_bdev -- unlock filesystem + * @bdev: blockdevice to unlock + * + * Unlocks the filesystem and marks it writeable again after freeze_bdev(). + */ +int thaw_bdev(struct block_device *bdev) +{ + struct super_block *sb; + int error = -EINVAL; + + mutex_lock(&bdev->bd_fsfreeze_mutex); + if (!bdev->bd_fsfreeze_count) + goto out; + + error = 0; + if (--bdev->bd_fsfreeze_count > 0) + goto out; + + sb = bdev->bd_fsfreeze_sb; + if (!sb) + goto out; + + if (sb->s_op->thaw_super) + error = sb->s_op->thaw_super(sb); + else + error = thaw_super(sb); + if (error) + bdev->bd_fsfreeze_count++; + else + bdev->bd_fsfreeze_sb = NULL; +out: + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return error; +} +EXPORT_SYMBOL(thaw_bdev); + +/** + * bdev_read_page() - Start reading a page from a block device + * @bdev: The device to read the page from + * @sector: The offset on the device to read the page to (need not be aligned) + * @page: The page to read + * + * On entry, the page should be locked. It will be unlocked when the page + * has been read. If the block driver implements rw_page synchronously, + * that will be true on exit from this function, but it need not be. + * + * Errors returned by this function are usually "soft", eg out of memory, or + * queue full; callers should try a different route to read this page rather + * than propagate an error back up the stack. + * + * Return: negative errno if an error occurs, 0 if submission was successful. + */ +int bdev_read_page(struct block_device *bdev, sector_t sector, + struct page *page) +{ + const struct block_device_operations *ops = bdev->bd_disk->fops; + int result = -EOPNOTSUPP; + + if (!ops->rw_page || bdev_get_integrity(bdev)) + return result; + + result = blk_queue_enter(bdev->bd_disk->queue, 0); + if (result) + return result; + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, + REQ_OP_READ); + blk_queue_exit(bdev->bd_disk->queue); + return result; +} + +/** + * bdev_write_page() - Start writing a page to a block device + * @bdev: The device to write the page to + * @sector: The offset on the device to write the page to (need not be aligned) + * @page: The page to write + * @wbc: The writeback_control for the write + * + * On entry, the page should be locked and not currently under writeback. + * On exit, if the write started successfully, the page will be unlocked and + * under writeback. If the write failed already (eg the driver failed to + * queue the page to the device), the page will still be locked. If the + * caller is a ->writepage implementation, it will need to unlock the page. + * + * Errors returned by this function are usually "soft", eg out of memory, or + * queue full; callers should try a different route to write this page rather + * than propagate an error back up the stack. + * + * Return: negative errno if an error occurs, 0 if submission was successful. + */ +int bdev_write_page(struct block_device *bdev, sector_t sector, + struct page *page, struct writeback_control *wbc) +{ + int result; + const struct block_device_operations *ops = bdev->bd_disk->fops; + + if (!ops->rw_page || bdev_get_integrity(bdev)) + return -EOPNOTSUPP; + result = blk_queue_enter(bdev->bd_disk->queue, 0); + if (result) + return result; + + set_page_writeback(page); + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, + REQ_OP_WRITE); + if (result) { + end_page_writeback(page); + } else { + clean_page_buffers(page); + unlock_page(page); + } + blk_queue_exit(bdev->bd_disk->queue); + return result; +} + +/* + * pseudo-fs + */ + +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock); +static struct kmem_cache * bdev_cachep __read_mostly; + +static struct inode *bdev_alloc_inode(struct super_block *sb) +{ + struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL); + + if (!ei) + return NULL; + memset(&ei->bdev, 0, sizeof(ei->bdev)); + return &ei->vfs_inode; +} + +static void bdev_free_inode(struct inode *inode) +{ + struct block_device *bdev = I_BDEV(inode); + + free_percpu(bdev->bd_stats); + kfree(bdev->bd_meta_info); + + if (!bdev_is_partition(bdev)) { + if (bdev->bd_disk && bdev->bd_disk->bdi) + bdi_put(bdev->bd_disk->bdi); + kfree(bdev->bd_disk); + } + + if (MAJOR(bdev->bd_dev) == BLOCK_EXT_MAJOR) + blk_free_ext_minor(MINOR(bdev->bd_dev)); + + kmem_cache_free(bdev_cachep, BDEV_I(inode)); +} + +static void init_once(void *data) +{ + struct bdev_inode *ei = data; + + inode_init_once(&ei->vfs_inode); +} + +static void bdev_evict_inode(struct inode *inode) +{ + truncate_inode_pages_final(&inode->i_data); + invalidate_inode_buffers(inode); /* is it needed here? */ + clear_inode(inode); +} + +static const struct super_operations bdev_sops = { + .statfs = simple_statfs, + .alloc_inode = bdev_alloc_inode, + .free_inode = bdev_free_inode, + .drop_inode = generic_delete_inode, + .evict_inode = bdev_evict_inode, +}; + +static int bd_init_fs_context(struct fs_context *fc) +{ + struct pseudo_fs_context *ctx = init_pseudo(fc, BDEVFS_MAGIC); + if (!ctx) + return -ENOMEM; + fc->s_iflags |= SB_I_CGROUPWB; + ctx->ops = &bdev_sops; + return 0; +} + +static struct file_system_type bd_type = { + .name = "bdev", + .init_fs_context = bd_init_fs_context, + .kill_sb = kill_anon_super, +}; + +struct super_block *blockdev_superblock __read_mostly; +EXPORT_SYMBOL_GPL(blockdev_superblock); + +void __init bdev_cache_init(void) +{ + int err; + static struct vfsmount *bd_mnt; + + bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode), + 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| + SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC), + init_once); + err = register_filesystem(&bd_type); + if (err) + panic("Cannot register bdev pseudo-fs"); + bd_mnt = kern_mount(&bd_type); + if (IS_ERR(bd_mnt)) + panic("Cannot create bdev pseudo-fs"); + blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */ +} + +struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) +{ + struct block_device *bdev; + struct inode *inode; + + inode = new_inode(blockdev_superblock); + if (!inode) + return NULL; + inode->i_mode = S_IFBLK; + inode->i_rdev = 0; + inode->i_data.a_ops = &def_blk_aops; + mapping_set_gfp_mask(&inode->i_data, GFP_USER); + + bdev = I_BDEV(inode); + mutex_init(&bdev->bd_fsfreeze_mutex); + spin_lock_init(&bdev->bd_size_lock); + bdev->bd_partno = partno; + bdev->bd_inode = inode; + bdev->bd_stats = alloc_percpu(struct disk_stats); + if (!bdev->bd_stats) { + iput(inode); + return NULL; + } + bdev->bd_disk = disk; + return bdev; +} + +void bdev_add(struct block_device *bdev, dev_t dev) +{ + bdev->bd_dev = dev; + bdev->bd_inode->i_rdev = dev; + bdev->bd_inode->i_ino = dev; + insert_inode_hash(bdev->bd_inode); +} + +long nr_blockdev_pages(void) +{ + struct inode *inode; + long ret = 0; + + spin_lock(&blockdev_superblock->s_inode_list_lock); + list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) + ret += inode->i_mapping->nrpages; + spin_unlock(&blockdev_superblock->s_inode_list_lock); + + return ret; +} + +/** + * bd_may_claim - test whether a block device can be claimed + * @bdev: block device of interest + * @whole: whole block device containing @bdev, may equal @bdev + * @holder: holder trying to claim @bdev + * + * Test whether @bdev can be claimed by @holder. + * + * CONTEXT: + * spin_lock(&bdev_lock). + * + * RETURNS: + * %true if @bdev can be claimed, %false otherwise. + */ +static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, + void *holder) +{ + if (bdev->bd_holder == holder) + return true; /* already a holder */ + else if (bdev->bd_holder != NULL) + return false; /* held by someone else */ + else if (whole == bdev) + return true; /* is a whole device which isn't held */ + + else if (whole->bd_holder == bd_may_claim) + return true; /* is a partition of a device that is being partitioned */ + else if (whole->bd_holder != NULL) + return false; /* is a partition of a held device */ + else + return true; /* is a partition of an un-held device */ +} + +/** + * bd_prepare_to_claim - claim a block device + * @bdev: block device of interest + * @holder: holder trying to claim @bdev + * + * Claim @bdev. This function fails if @bdev is already claimed by another + * holder and waits if another claiming is in progress. return, the caller + * has ownership of bd_claiming and bd_holder[s]. + * + * RETURNS: + * 0 if @bdev can be claimed, -EBUSY otherwise. + */ +int bd_prepare_to_claim(struct block_device *bdev, void *holder) +{ + struct block_device *whole = bdev_whole(bdev); + + if (WARN_ON_ONCE(!holder)) + return -EINVAL; +retry: + spin_lock(&bdev_lock); + /* if someone else claimed, fail */ + if (!bd_may_claim(bdev, whole, holder)) { + spin_unlock(&bdev_lock); + return -EBUSY; + } + + /* if claiming is already in progress, wait for it to finish */ + if (whole->bd_claiming) { + wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0); + DEFINE_WAIT(wait); + + prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&bdev_lock); + schedule(); + finish_wait(wq, &wait); + goto retry; + } + + /* yay, all mine */ + whole->bd_claiming = holder; + spin_unlock(&bdev_lock); + return 0; +} +EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */ + +static void bd_clear_claiming(struct block_device *whole, void *holder) +{ + lockdep_assert_held(&bdev_lock); + /* tell others that we're done */ + BUG_ON(whole->bd_claiming != holder); + whole->bd_claiming = NULL; + wake_up_bit(&whole->bd_claiming, 0); +} + +/** + * bd_finish_claiming - finish claiming of a block device + * @bdev: block device of interest + * @holder: holder that has claimed @bdev + * + * Finish exclusive open of a block device. Mark the device as exlusively + * open by the holder and wake up all waiters for exclusive open to finish. + */ +static void bd_finish_claiming(struct block_device *bdev, void *holder) +{ + struct block_device *whole = bdev_whole(bdev); + + spin_lock(&bdev_lock); + BUG_ON(!bd_may_claim(bdev, whole, holder)); + /* + * Note that for a whole device bd_holders will be incremented twice, + * and bd_holder will be set to bd_may_claim before being set to holder + */ + whole->bd_holders++; + whole->bd_holder = bd_may_claim; + bdev->bd_holders++; + bdev->bd_holder = holder; + bd_clear_claiming(whole, holder); + spin_unlock(&bdev_lock); +} + +/** + * bd_abort_claiming - abort claiming of a block device + * @bdev: block device of interest + * @holder: holder that has claimed @bdev + * + * Abort claiming of a block device when the exclusive open failed. This can be + * also used when exclusive open is not actually desired and we just needed + * to block other exclusive openers for a while. + */ +void bd_abort_claiming(struct block_device *bdev, void *holder) +{ + spin_lock(&bdev_lock); + bd_clear_claiming(bdev_whole(bdev), holder); + spin_unlock(&bdev_lock); +} +EXPORT_SYMBOL(bd_abort_claiming); + +static void blkdev_flush_mapping(struct block_device *bdev) +{ + WARN_ON_ONCE(bdev->bd_holders); + sync_blockdev(bdev); + kill_bdev(bdev); + bdev_write_inode(bdev); +} + +static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) +{ + struct gendisk *disk = bdev->bd_disk; + int ret = 0; + + if (disk->fops->open) { + ret = disk->fops->open(bdev, mode); + if (ret) { + /* avoid ghost partitions on a removed medium */ + if (ret == -ENOMEDIUM && + test_bit(GD_NEED_PART_SCAN, &disk->state)) + bdev_disk_changed(disk, true); + return ret; + } + } + + if (!bdev->bd_openers) + set_init_blocksize(bdev); + if (test_bit(GD_NEED_PART_SCAN, &disk->state)) + bdev_disk_changed(disk, false); + bdev->bd_openers++; + return 0;; +} + +static void blkdev_put_whole(struct block_device *bdev, fmode_t mode) +{ + if (!--bdev->bd_openers) + blkdev_flush_mapping(bdev); + if (bdev->bd_disk->fops->release) + bdev->bd_disk->fops->release(bdev->bd_disk, mode); +} + +static int blkdev_get_part(struct block_device *part, fmode_t mode) +{ + struct gendisk *disk = part->bd_disk; + int ret; + + if (part->bd_openers) + goto done; + + ret = blkdev_get_whole(bdev_whole(part), mode); + if (ret) + return ret; + + ret = -ENXIO; + if (!bdev_nr_sectors(part)) + goto out_blkdev_put; + + disk->open_partitions++; + set_init_blocksize(part); +done: + part->bd_openers++; + return 0; + +out_blkdev_put: + blkdev_put_whole(bdev_whole(part), mode); + return ret; +} + +static void blkdev_put_part(struct block_device *part, fmode_t mode) +{ + struct block_device *whole = bdev_whole(part); + + if (--part->bd_openers) + return; + blkdev_flush_mapping(part); + whole->bd_disk->open_partitions--; + blkdev_put_whole(whole, mode); +} + +struct block_device *blkdev_get_no_open(dev_t dev) +{ + struct block_device *bdev; + struct inode *inode; + + inode = ilookup(blockdev_superblock, dev); + if (!inode) { + blk_request_module(dev); + inode = ilookup(blockdev_superblock, dev); + if (!inode) + return NULL; + } + + /* switch from the inode reference to a device mode one: */ + bdev = &BDEV_I(inode)->bdev; + if (!kobject_get_unless_zero(&bdev->bd_device.kobj)) + bdev = NULL; + iput(inode); + + if (!bdev) + return NULL; + if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN) || + !try_module_get(bdev->bd_disk->fops->owner)) { + put_device(&bdev->bd_device); + return NULL; + } + + return bdev; +} + +void blkdev_put_no_open(struct block_device *bdev) +{ + module_put(bdev->bd_disk->fops->owner); + put_device(&bdev->bd_device); +} + +/** + * blkdev_get_by_dev - open a block device by device number + * @dev: device number of block device to open + * @mode: FMODE_* mask + * @holder: exclusive holder identifier + * + * Open the block device described by device number @dev. If @mode includes + * %FMODE_EXCL, the block device is opened with exclusive access. Specifying + * %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may nest for + * the same @holder. + * + * Use this interface ONLY if you really do not have anything better - i.e. when + * you are behind a truly sucky interface and all you are given is a device + * number. Everything else should use blkdev_get_by_path(). + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * Reference to the block_device on success, ERR_PTR(-errno) on failure. + */ +struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) +{ + bool unblock_events = true; + struct block_device *bdev; + struct gendisk *disk; + int ret; + + ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, + MAJOR(dev), MINOR(dev), + ((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) | + ((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0)); + if (ret) + return ERR_PTR(ret); + + bdev = blkdev_get_no_open(dev); + if (!bdev) + return ERR_PTR(-ENXIO); + disk = bdev->bd_disk; + + if (mode & FMODE_EXCL) { + ret = bd_prepare_to_claim(bdev, holder); + if (ret) + goto put_blkdev; + } + + disk_block_events(disk); + + mutex_lock(&disk->open_mutex); + ret = -ENXIO; + if (!disk_live(disk)) + goto abort_claiming; + if (bdev_is_partition(bdev)) + ret = blkdev_get_part(bdev, mode); + else + ret = blkdev_get_whole(bdev, mode); + if (ret) + goto abort_claiming; + if (mode & FMODE_EXCL) { + bd_finish_claiming(bdev, holder); + + /* + * Block event polling for write claims if requested. Any write + * holder makes the write_holder state stick until all are + * released. This is good enough and tracking individual + * writeable reference is too fragile given the way @mode is + * used in blkdev_get/put(). + */ + if ((mode & FMODE_WRITE) && !bdev->bd_write_holder && + (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) { + bdev->bd_write_holder = true; + unblock_events = false; + } + } + mutex_unlock(&disk->open_mutex); + + if (unblock_events) + disk_unblock_events(disk); + return bdev; + +abort_claiming: + if (mode & FMODE_EXCL) + bd_abort_claiming(bdev, holder); + mutex_unlock(&disk->open_mutex); + disk_unblock_events(disk); +put_blkdev: + blkdev_put_no_open(bdev); + return ERR_PTR(ret); +} +EXPORT_SYMBOL(blkdev_get_by_dev); + +/** + * blkdev_get_by_path - open a block device by name + * @path: path to the block device to open + * @mode: FMODE_* mask + * @holder: exclusive holder identifier + * + * Open the block device described by the device file at @path. If @mode + * includes %FMODE_EXCL, the block device is opened with exclusive access. + * Specifying %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may + * nest for the same @holder. + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * Reference to the block_device on success, ERR_PTR(-errno) on failure. + */ +struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, + void *holder) +{ + struct block_device *bdev; + dev_t dev; + int error; + + error = lookup_bdev(path, &dev); + if (error) + return ERR_PTR(error); + + bdev = blkdev_get_by_dev(dev, mode, holder); + if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) { + blkdev_put(bdev, mode); + return ERR_PTR(-EACCES); + } + + return bdev; +} +EXPORT_SYMBOL(blkdev_get_by_path); + +void blkdev_put(struct block_device *bdev, fmode_t mode) +{ + struct gendisk *disk = bdev->bd_disk; + + /* + * Sync early if it looks like we're the last one. If someone else + * opens the block device between now and the decrement of bd_openers + * then we did a sync that we didn't need to, but that's not the end + * of the world and we want to avoid long (could be several minute) + * syncs while holding the mutex. + */ + if (bdev->bd_openers == 1) + sync_blockdev(bdev); + + mutex_lock(&disk->open_mutex); + if (mode & FMODE_EXCL) { + struct block_device *whole = bdev_whole(bdev); + bool bdev_free; + + /* + * Release a claim on the device. The holder fields + * are protected with bdev_lock. open_mutex is to + * synchronize disk_holder unlinking. + */ + spin_lock(&bdev_lock); + + WARN_ON_ONCE(--bdev->bd_holders < 0); + WARN_ON_ONCE(--whole->bd_holders < 0); + + if ((bdev_free = !bdev->bd_holders)) + bdev->bd_holder = NULL; + if (!whole->bd_holders) + whole->bd_holder = NULL; + + spin_unlock(&bdev_lock); + + /* + * If this was the last claim, remove holder link and + * unblock evpoll if it was a write holder. + */ + if (bdev_free && bdev->bd_write_holder) { + disk_unblock_events(disk); + bdev->bd_write_holder = false; + } + } + + /* + * Trigger event checking and tell drivers to flush MEDIA_CHANGE + * event. This is to ensure detection of media removal commanded + * from userland - e.g. eject(1). + */ + disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE); + + if (bdev_is_partition(bdev)) + blkdev_put_part(bdev, mode); + else + blkdev_put_whole(bdev, mode); + mutex_unlock(&disk->open_mutex); + + blkdev_put_no_open(bdev); +} +EXPORT_SYMBOL(blkdev_put); + +/** + * lookup_bdev - lookup a struct block_device by name + * @pathname: special file representing the block device + * @dev: return value of the block device's dev_t + * + * Get a reference to the blockdevice at @pathname in the current + * namespace if possible and return it. Return ERR_PTR(error) + * otherwise. + */ +int lookup_bdev(const char *pathname, dev_t *dev) +{ + struct inode *inode; + struct path path; + int error; + + if (!pathname || !*pathname) + return -EINVAL; + + error = kern_path(pathname, LOOKUP_FOLLOW, &path); + if (error) + return error; + + inode = d_backing_inode(path.dentry); + error = -ENOTBLK; + if (!S_ISBLK(inode->i_mode)) + goto out_path_put; + error = -EACCES; + if (!may_open_dev(&path)) + goto out_path_put; + + *dev = inode->i_rdev; + error = 0; +out_path_put: + path_put(&path); + return error; +} +EXPORT_SYMBOL(lookup_bdev); + +int __invalidate_device(struct block_device *bdev, bool kill_dirty) +{ + struct super_block *sb = get_super(bdev); + int res = 0; + + if (sb) { + /* + * no need to lock the super, get_super holds the + * read mutex so the filesystem cannot go away + * under us (->put_super runs with the write lock + * hold). + */ + shrink_dcache_sb(sb); + res = invalidate_inodes(sb, kill_dirty); + drop_super(sb); + } + invalidate_bdev(bdev); + return res; +} +EXPORT_SYMBOL(__invalidate_device); + +void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) +{ + struct inode *inode, *old_inode = NULL; + + spin_lock(&blockdev_superblock->s_inode_list_lock); + list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) { + struct address_space *mapping = inode->i_mapping; + struct block_device *bdev; + + spin_lock(&inode->i_lock); + if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || + mapping->nrpages == 0) { + spin_unlock(&inode->i_lock); + continue; + } + __iget(inode); + spin_unlock(&inode->i_lock); + spin_unlock(&blockdev_superblock->s_inode_list_lock); + /* + * We hold a reference to 'inode' so it couldn't have been + * removed from s_inodes list while we dropped the + * s_inode_list_lock We cannot iput the inode now as we can + * be holding the last reference and we cannot iput it under + * s_inode_list_lock. So we keep the reference and iput it + * later. + */ + iput(old_inode); + old_inode = inode; + bdev = I_BDEV(inode); + + mutex_lock(&bdev->bd_disk->open_mutex); + if (bdev->bd_openers) + func(bdev, arg); + mutex_unlock(&bdev->bd_disk->open_mutex); + + spin_lock(&blockdev_superblock->s_inode_list_lock); + } + spin_unlock(&blockdev_superblock->s_inode_list_lock); + iput(old_inode); +} diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index e2f14508f2d6..85b8e1c3a762 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -666,6 +666,12 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, bfq_put_idle_entity(bfq_entity_service_tree(entity), entity); bfqg_and_blkg_put(bfqq_group(bfqq)); + if (entity->parent && + entity->parent->last_bfqq_created == bfqq) + entity->parent->last_bfqq_created = NULL; + else if (bfqd->last_bfqq_created == bfqq) + bfqd->last_bfqq_created = NULL; + entity->parent = bfqg->my_entity; entity->sched_data = &bfqg->sched_data; /* pin down bfqg and its associated blkg */ diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index dd13c2bbc29c..480e1a134859 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2662,15 +2662,6 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) * are likely to increase the throughput. */ bfqq->new_bfqq = new_bfqq; - /* - * The above assignment schedules the following redirections: - * each time some I/O for bfqq arrives, the process that - * generated that I/O is disassociated from bfqq and - * associated with new_bfqq. Here we increases new_bfqq->ref - * in advance, adding the number of processes that are - * expected to be associated with new_bfqq as they happen to - * issue I/O. - */ new_bfqq->ref += process_refs; return new_bfqq; } @@ -2733,10 +2724,6 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, { struct bfq_queue *in_service_bfqq, *new_bfqq; - /* if a merge has already been setup, then proceed with that first */ - if (bfqq->new_bfqq) - return bfqq->new_bfqq; - /* * Check delayed stable merge for rotational or non-queueing * devs. For this branch to be executed, bfqq must not be @@ -2838,6 +2825,9 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, if (bfq_too_late_for_merging(bfqq)) return NULL; + if (bfqq->new_bfqq) + return bfqq->new_bfqq; + if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq)) return NULL; diff --git a/block/bio.c b/block/bio.c index 5df3dd282e40..a6fb6a0b4295 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1466,7 +1466,7 @@ again: if (!bio_integrity_endio(bio)) return; - if (bio->bi_bdev) + if (bio->bi_bdev && bio_flagged(bio, BIO_TRACKED)) rq_qos_done_bio(bio->bi_bdev->bd_disk->queue, bio); if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 3c88a79a319b..9a1c5839dd46 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1182,10 +1182,6 @@ int blkcg_init_queue(struct request_queue *q) if (preloaded) radix_tree_preload_end(); - ret = blk_iolatency_init(q); - if (ret) - goto err_destroy_all; - ret = blk_ioprio_init(q); if (ret) goto err_destroy_all; @@ -1194,6 +1190,12 @@ int blkcg_init_queue(struct request_queue *q) if (ret) goto err_destroy_all; + ret = blk_iolatency_init(q); + if (ret) { + blk_throtl_exit(q); + goto err_destroy_all; + } + return 0; err_destroy_all: @@ -1364,10 +1366,14 @@ enomem: /* alloc failed, nothing's initialized yet, free everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { + struct blkcg *blkcg = blkg->blkcg; + + spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } + spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; @@ -1399,12 +1405,16 @@ void blkcg_deactivate_policy(struct request_queue *q, __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { + struct blkcg *blkcg = blkg->blkcg; + + spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } + spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); @@ -1887,10 +1897,11 @@ void blk_cgroup_bio_start(struct bio *bio) { int rwd = blk_cgroup_io_type(bio), cpu; struct blkg_iostat_set *bis; + unsigned long flags; cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); - u64_stats_update_begin(&bis->sync); + flags = u64_stats_update_begin_irqsave(&bis->sync); /* * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split @@ -1902,7 +1913,7 @@ void blk_cgroup_bio_start(struct bio *bio) } bis->cur.ios[rwd]++; - u64_stats_update_end(&bis->sync); + u64_stats_update_end_irqrestore(&bis->sync, flags); if (cgroup_subsys_on_dfl(io_cgrp_subsys)) cgroup_rstat_updated(bio->bi_blkg->blkcg->css.cgroup, cpu); put_cpu(); diff --git a/block/blk-core.c b/block/blk-core.c index 5454db2fa263..4d8f5fe91588 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -49,7 +49,6 @@ #include "blk-mq.h" #include "blk-mq-sched.h" #include "blk-pm.h" -#include "blk-rq-qos.h" struct dentry *blk_debugfs_root; @@ -337,23 +336,25 @@ void blk_put_queue(struct request_queue *q) } EXPORT_SYMBOL(blk_put_queue); -void blk_set_queue_dying(struct request_queue *q) +void blk_queue_start_drain(struct request_queue *q) { - blk_queue_flag_set(QUEUE_FLAG_DYING, q); - /* * When queue DYING flag is set, we need to block new req * entering queue, so we call blk_freeze_queue_start() to * prevent I/O from crossing blk_queue_enter(). */ blk_freeze_queue_start(q); - if (queue_is_mq(q)) blk_mq_wake_waiters(q); - /* Make blk_queue_enter() reexamine the DYING flag. */ wake_up_all(&q->mq_freeze_wq); } + +void blk_set_queue_dying(struct request_queue *q) +{ + blk_queue_flag_set(QUEUE_FLAG_DYING, q); + blk_queue_start_drain(q); +} EXPORT_SYMBOL_GPL(blk_set_queue_dying); /** @@ -385,13 +386,8 @@ void blk_cleanup_queue(struct request_queue *q) */ blk_freeze_queue(q); - rq_qos_exit(q); - blk_queue_flag_set(QUEUE_FLAG_DEAD, q); - /* for synchronous bio-based driver finish in-flight integrity i/o */ - blk_flush_integrity(); - blk_sync_queue(q); if (queue_is_mq(q)) blk_mq_exit_queue(q); @@ -416,6 +412,30 @@ void blk_cleanup_queue(struct request_queue *q) } EXPORT_SYMBOL(blk_cleanup_queue); +static bool blk_try_enter_queue(struct request_queue *q, bool pm) +{ + rcu_read_lock(); + if (!percpu_ref_tryget_live(&q->q_usage_counter)) + goto fail; + + /* + * The code that increments the pm_only counter must ensure that the + * counter is globally visible before the queue is unfrozen. + */ + if (blk_queue_pm_only(q) && + (!pm || queue_rpm_status(q) == RPM_SUSPENDED)) + goto fail_put; + + rcu_read_unlock(); + return true; + +fail_put: + percpu_ref_put(&q->q_usage_counter); +fail: + rcu_read_unlock(); + return false; +} + /** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer @@ -425,40 +445,18 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) { const bool pm = flags & BLK_MQ_REQ_PM; - while (true) { - bool success = false; - - rcu_read_lock(); - if (percpu_ref_tryget_live(&q->q_usage_counter)) { - /* - * The code that increments the pm_only counter is - * responsible for ensuring that that counter is - * globally visible before the queue is unfrozen. - */ - if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) || - !blk_queue_pm_only(q)) { - success = true; - } else { - percpu_ref_put(&q->q_usage_counter); - } - } - rcu_read_unlock(); - - if (success) - return 0; - + while (!blk_try_enter_queue(q, pm)) { if (flags & BLK_MQ_REQ_NOWAIT) return -EBUSY; /* - * read pair of barrier in blk_freeze_queue_start(), - * we need to order reading __PERCPU_REF_DEAD flag of - * .q_usage_counter and reading .mq_freeze_depth or - * queue dying flag, otherwise the following wait may - * never return if the two reads are reordered. + * read pair of barrier in blk_freeze_queue_start(), we need to + * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and + * reading .mq_freeze_depth or queue dying flag, otherwise the + * following wait may never return if the two reads are + * reordered. */ smp_rmb(); - wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(pm, q)) || @@ -466,23 +464,43 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) if (blk_queue_dying(q)) return -ENODEV; } + + return 0; } static inline int bio_queue_enter(struct bio *bio) { - struct request_queue *q = bio->bi_bdev->bd_disk->queue; - bool nowait = bio->bi_opf & REQ_NOWAIT; - int ret; + struct gendisk *disk = bio->bi_bdev->bd_disk; + struct request_queue *q = disk->queue; - ret = blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0); - if (unlikely(ret)) { - if (nowait && !blk_queue_dying(q)) + while (!blk_try_enter_queue(q, false)) { + if (bio->bi_opf & REQ_NOWAIT) { + if (test_bit(GD_DEAD, &disk->state)) + goto dead; bio_wouldblock_error(bio); - else - bio_io_error(bio); + return -EBUSY; + } + + /* + * read pair of barrier in blk_freeze_queue_start(), we need to + * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and + * reading .mq_freeze_depth or queue dying flag, otherwise the + * following wait may never return if the two reads are + * reordered. + */ + smp_rmb(); + wait_event(q->mq_freeze_wq, + (!q->mq_freeze_depth && + blk_pm_resume_queue(false, q)) || + test_bit(GD_DEAD, &disk->state)); + if (test_bit(GD_DEAD, &disk->state)) + goto dead; } - return ret; + return 0; +dead: + bio_io_error(bio); + return -ENODEV; } void blk_queue_exit(struct request_queue *q) @@ -899,11 +917,18 @@ static blk_qc_t __submit_bio(struct bio *bio) struct gendisk *disk = bio->bi_bdev->bd_disk; blk_qc_t ret = BLK_QC_T_NONE; - if (blk_crypto_bio_prep(&bio)) { - if (!disk->fops->submit_bio) - return blk_mq_submit_bio(bio); + if (unlikely(bio_queue_enter(bio) != 0)) + return BLK_QC_T_NONE; + + if (!submit_bio_checks(bio) || !blk_crypto_bio_prep(&bio)) + goto queue_exit; + if (disk->fops->submit_bio) { ret = disk->fops->submit_bio(bio); + goto queue_exit; } + return blk_mq_submit_bio(bio); + +queue_exit: blk_queue_exit(disk->queue); return ret; } @@ -941,9 +966,6 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio) struct request_queue *q = bio->bi_bdev->bd_disk->queue; struct bio_list lower, same; - if (unlikely(bio_queue_enter(bio) != 0)) - continue; - /* * Create a fresh bio_list for all subordinate requests. */ @@ -979,23 +1001,12 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio) static blk_qc_t __submit_bio_noacct_mq(struct bio *bio) { struct bio_list bio_list[2] = { }; - blk_qc_t ret = BLK_QC_T_NONE; + blk_qc_t ret; current->bio_list = bio_list; do { - struct gendisk *disk = bio->bi_bdev->bd_disk; - - if (unlikely(bio_queue_enter(bio) != 0)) - continue; - - if (!blk_crypto_bio_prep(&bio)) { - blk_queue_exit(disk->queue); - ret = BLK_QC_T_NONE; - continue; - } - - ret = blk_mq_submit_bio(bio); + ret = __submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0]))); current->bio_list = NULL; @@ -1013,9 +1024,6 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio) */ blk_qc_t submit_bio_noacct(struct bio *bio) { - if (!submit_bio_checks(bio)) - return BLK_QC_T_NONE; - /* * We only want one ->submit_bio to be active at a time, else stack * usage with stacked devices could be a problem. Use current->bio_list diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 69a12177dfb6..16d5d5338392 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -426,8 +426,15 @@ EXPORT_SYMBOL(blk_integrity_register); */ void blk_integrity_unregister(struct gendisk *disk) { + struct blk_integrity *bi = &disk->queue->integrity; + + if (!bi->profile) + return; + + /* ensure all bios are off the integrity workqueue */ + blk_flush_integrity(); blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue); - memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity)); + memset(bi, 0, sizeof(*bi)); } EXPORT_SYMBOL(blk_integrity_unregister); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 4b66d2776eda..3b38d15723de 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -129,6 +129,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(PCI_P2PDMA), QUEUE_FLAG_NAME(ZONE_RESETALL), QUEUE_FLAG_NAME(RQ_ALLOC_TIME), + QUEUE_FLAG_NAME(HCTX_ACTIVE), QUEUE_FLAG_NAME(NOWAIT), }; #undef QUEUE_FLAG_NAME diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 86f87346232a..ff5caeb82542 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -208,7 +208,7 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, spin_lock_irqsave(&tags->lock, flags); rq = tags->rqs[bitnr]; - if (!rq || !refcount_inc_not_zero(&rq->ref)) + if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref)) rq = NULL; spin_unlock_irqrestore(&tags->lock, flags); return rq; diff --git a/block/blk-mq.c b/block/blk-mq.c index 65d3a63aecc6..652a31fc3bb3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -188,9 +188,11 @@ void blk_mq_freeze_queue(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue); -void blk_mq_unfreeze_queue(struct request_queue *q) +void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic) { mutex_lock(&q->mq_freeze_lock); + if (force_atomic) + q->q_usage_counter.data->force_atomic = true; q->mq_freeze_depth--; WARN_ON_ONCE(q->mq_freeze_depth < 0); if (!q->mq_freeze_depth) { @@ -199,6 +201,11 @@ void blk_mq_unfreeze_queue(struct request_queue *q) } mutex_unlock(&q->mq_freeze_lock); } + +void blk_mq_unfreeze_queue(struct request_queue *q) +{ + __blk_mq_unfreeze_queue(q, false); +} EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); /* @@ -1318,6 +1325,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, int errors, queued; blk_status_t ret = BLK_STS_OK; LIST_HEAD(zone_list); + bool needs_resource = false; if (list_empty(list)) return false; @@ -1363,6 +1371,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, queued++; break; case BLK_STS_RESOURCE: + needs_resource = true; + fallthrough; case BLK_STS_DEV_RESOURCE: blk_mq_handle_dev_resource(rq, list); goto out; @@ -1373,6 +1383,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, * accept. */ blk_mq_handle_zone_resource(rq, &zone_list); + needs_resource = true; break; default: errors++; @@ -1399,7 +1410,6 @@ out: /* For non-shared tags, the RESTART check will suffice */ bool no_tag = prep == PREP_DISPATCH_NO_TAG && (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED); - bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET; if (nr_budgets) blk_mq_release_budgets(q, list); @@ -1440,14 +1450,16 @@ out: * If driver returns BLK_STS_RESOURCE and SCHED_RESTART * bit is set, run queue after a delay to avoid IO stalls * that could otherwise occur if the queue is idle. We'll do - * similar if we couldn't get budget and SCHED_RESTART is set. + * similar if we couldn't get budget or couldn't lock a zone + * and SCHED_RESTART is set. */ needs_restart = blk_mq_sched_needs_restart(hctx); + if (prep == PREP_DISPATCH_NO_BUDGET) + needs_resource = true; if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); - else if (needs_restart && (ret == BLK_STS_RESOURCE || - no_budget_avail)) + else if (needs_restart && needs_resource) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); blk_mq_update_dispatch_busy(hctx, true); @@ -2135,6 +2147,18 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) } } +/* + * Allow 4x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple + * queues. This is important for md arrays to benefit from merging + * requests. + */ +static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) +{ + if (plug->multiple_queues) + return BLK_MAX_REQUEST_COUNT * 4; + return BLK_MAX_REQUEST_COUNT; +} + /** * blk_mq_submit_bio - Create and send a request to block device. * @bio: Bio pointer. @@ -2231,7 +2255,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) else last = list_entry_rq(plug->mq_list.prev); - if (request_count >= BLK_MAX_REQUEST_COUNT || (last && + if (request_count >= blk_plug_max_rq_count(plug) || (last && blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { blk_flush_plug_list(plug, false); trace_block_plug(q); diff --git a/block/blk-settings.c b/block/blk-settings.c index a7c857ad7d10..b880c70e22e4 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -842,6 +842,24 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging); +static bool disk_has_partitions(struct gendisk *disk) +{ + unsigned long idx; + struct block_device *part; + bool ret = false; + + rcu_read_lock(); + xa_for_each(&disk->part_tbl, idx, part) { + if (bdev_is_partition(part)) { + ret = true; + break; + } + } + rcu_read_unlock(); + + return ret; +} + /** * blk_queue_set_zoned - configure a disk queue zoned model. * @disk: the gendisk of the queue to configure @@ -876,7 +894,7 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) * we do nothing special as far as the block layer is concerned. */ if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || - !xa_empty(&disk->part_tbl)) + disk_has_partitions(disk)) model = BLK_ZONED_NONE; break; case BLK_ZONED_NONE: diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 55c49015e533..7c4e7993ba97 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2458,6 +2458,7 @@ int blk_throtl_init(struct request_queue *q) void blk_throtl_exit(struct request_queue *q) { BUG_ON(!q->td); + del_timer_sync(&q->td->service_queue.pending_timer); throtl_shutdown_wq(q); blkcg_deactivate_policy(q, &blkcg_policy_throtl); free_percpu(q->td->latency_buckets[READ]); diff --git a/block/blk.h b/block/blk.h index 8c96b0c90c48..6c3c00a8fe19 100644 --- a/block/blk.h +++ b/block/blk.h @@ -51,6 +51,8 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, void blk_free_flush_queue(struct blk_flush_queue *q); void blk_freeze_queue(struct request_queue *q); +void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic); +void blk_queue_start_drain(struct request_queue *q); #define BIO_INLINE_VECS 4 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs, @@ -373,4 +375,6 @@ static inline void bio_clear_hipri(struct bio *bio) bio->bi_opf &= ~REQ_HIPRI; } +extern const struct address_space_operations def_blk_aops; + #endif /* BLK_INTERNAL_H */ diff --git a/block/bsg.c b/block/bsg.c index 351095193788..882f56bff14f 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -165,13 +165,20 @@ static const struct file_operations bsg_fops = { .llseek = default_llseek, }; +static void bsg_device_release(struct device *dev) +{ + struct bsg_device *bd = container_of(dev, struct bsg_device, device); + + ida_simple_remove(&bsg_minor_ida, MINOR(bd->device.devt)); + kfree(bd); +} + void bsg_unregister_queue(struct bsg_device *bd) { if (bd->queue->kobj.sd) sysfs_remove_link(&bd->queue->kobj, "bsg"); cdev_device_del(&bd->cdev, &bd->device); - ida_simple_remove(&bsg_minor_ida, MINOR(bd->device.devt)); - kfree(bd); + put_device(&bd->device); } EXPORT_SYMBOL_GPL(bsg_unregister_queue); @@ -193,11 +200,13 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, if (ret < 0) { if (ret == -ENOSPC) dev_err(parent, "bsg: too many bsg devices\n"); - goto out_kfree; + kfree(bd); + return ERR_PTR(ret); } bd->device.devt = MKDEV(bsg_major, ret); bd->device.class = bsg_class; bd->device.parent = parent; + bd->device.release = bsg_device_release; dev_set_name(&bd->device, "%s", name); device_initialize(&bd->device); @@ -205,7 +214,7 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, bd->cdev.owner = THIS_MODULE; ret = cdev_device_add(&bd->cdev, &bd->device); if (ret) - goto out_ida_remove; + goto out_put_device; if (q->kobj.sd) { ret = sysfs_create_link(&q->kobj, &bd->device.kobj, "bsg"); @@ -217,10 +226,8 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, out_device_del: cdev_device_del(&bd->cdev, &bd->device); -out_ida_remove: - ida_simple_remove(&bsg_minor_ida, MINOR(bd->device.devt)); -out_kfree: - kfree(bd); +out_put_device: + put_device(&bd->device); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(bsg_register_queue); diff --git a/block/fops.c b/block/fops.c new file mode 100644 index 000000000000..1e970c247e0e --- /dev/null +++ b/block/fops.c @@ -0,0 +1,639 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE + * Copyright (C) 2016 - 2020 Christoph Hellwig + */ +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/mpage.h> +#include <linux/uio.h> +#include <linux/namei.h> +#include <linux/task_io_accounting_ops.h> +#include <linux/falloc.h> +#include <linux/suspend.h> +#include <linux/fs.h> +#include "blk.h" + +static struct inode *bdev_file_inode(struct file *file) +{ + return file->f_mapping->host; +} + +static int blkdev_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh, int create) +{ + bh->b_bdev = I_BDEV(inode); + bh->b_blocknr = iblock; + set_buffer_mapped(bh); + return 0; +} + +static unsigned int dio_bio_write_op(struct kiocb *iocb) +{ + unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; + + /* avoid the need for a I/O completion work item */ + if (iocb->ki_flags & IOCB_DSYNC) + op |= REQ_FUA; + return op; +} + +#define DIO_INLINE_BIO_VECS 4 + +static void blkdev_bio_end_io_simple(struct bio *bio) +{ + struct task_struct *waiter = bio->bi_private; + + WRITE_ONCE(bio->bi_private, NULL); + blk_wake_io_task(waiter); +} + +static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, + struct iov_iter *iter, unsigned int nr_pages) +{ + struct file *file = iocb->ki_filp; + struct block_device *bdev = I_BDEV(bdev_file_inode(file)); + struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs; + loff_t pos = iocb->ki_pos; + bool should_dirty = false; + struct bio bio; + ssize_t ret; + blk_qc_t qc; + + if ((pos | iov_iter_alignment(iter)) & + (bdev_logical_block_size(bdev) - 1)) + return -EINVAL; + + if (nr_pages <= DIO_INLINE_BIO_VECS) + vecs = inline_vecs; + else { + vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec), + GFP_KERNEL); + if (!vecs) + return -ENOMEM; + } + + bio_init(&bio, vecs, nr_pages); + bio_set_dev(&bio, bdev); + bio.bi_iter.bi_sector = pos >> 9; + bio.bi_write_hint = iocb->ki_hint; + bio.bi_private = current; + bio.bi_end_io = blkdev_bio_end_io_simple; + bio.bi_ioprio = iocb->ki_ioprio; + + ret = bio_iov_iter_get_pages(&bio, iter); + if (unlikely(ret)) + goto out; + ret = bio.bi_iter.bi_size; + + if (iov_iter_rw(iter) == READ) { + bio.bi_opf = REQ_OP_READ; + if (iter_is_iovec(iter)) + should_dirty = true; + } else { + bio.bi_opf = dio_bio_write_op(iocb); + task_io_account_write(ret); + } + if (iocb->ki_flags & IOCB_NOWAIT) + bio.bi_opf |= REQ_NOWAIT; + if (iocb->ki_flags & IOCB_HIPRI) + bio_set_polled(&bio, iocb); + + qc = submit_bio(&bio); + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (!READ_ONCE(bio.bi_private)) + break; + if (!(iocb->ki_flags & IOCB_HIPRI) || + !blk_poll(bdev_get_queue(bdev), qc, true)) + blk_io_schedule(); + } + __set_current_state(TASK_RUNNING); + + bio_release_pages(&bio, should_dirty); + if (unlikely(bio.bi_status)) + ret = blk_status_to_errno(bio.bi_status); + +out: + if (vecs != inline_vecs) + kfree(vecs); + + bio_uninit(&bio); + + return ret; +} + +struct blkdev_dio { + union { + struct kiocb *iocb; + struct task_struct *waiter; + }; + size_t size; + atomic_t ref; + bool multi_bio : 1; + bool should_dirty : 1; + bool is_sync : 1; + struct bio bio; +}; + +static struct bio_set blkdev_dio_pool; + +static int blkdev_iopoll(struct kiocb *kiocb, bool wait) +{ + struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host); + struct request_queue *q = bdev_get_queue(bdev); + + return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait); +} + +static void blkdev_bio_end_io(struct bio *bio) +{ + struct blkdev_dio *dio = bio->bi_private; + bool should_dirty = dio->should_dirty; + + if (bio->bi_status && !dio->bio.bi_status) + dio->bio.bi_status = bio->bi_status; + + if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) { + if (!dio->is_sync) { + struct kiocb *iocb = dio->iocb; + ssize_t ret; + + if (likely(!dio->bio.bi_status)) { + ret = dio->size; + iocb->ki_pos += ret; + } else { + ret = blk_status_to_errno(dio->bio.bi_status); + } + + dio->iocb->ki_complete(iocb, ret, 0); + if (dio->multi_bio) + bio_put(&dio->bio); + } else { + struct task_struct *waiter = dio->waiter; + + WRITE_ONCE(dio->waiter, NULL); + blk_wake_io_task(waiter); + } + } + + if (should_dirty) { + bio_check_pages_dirty(bio); + } else { + bio_release_pages(bio, false); + bio_put(bio); + } +} + +static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + unsigned int nr_pages) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = bdev_file_inode(file); + struct block_device *bdev = I_BDEV(inode); + struct blk_plug plug; + struct blkdev_dio *dio; + struct bio *bio; + bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0; + bool is_read = (iov_iter_rw(iter) == READ), is_sync; + loff_t pos = iocb->ki_pos; + blk_qc_t qc = BLK_QC_T_NONE; + int ret = 0; + + if ((pos | iov_iter_alignment(iter)) & + (bdev_logical_block_size(bdev) - 1)) + return -EINVAL; + + bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool); + + dio = container_of(bio, struct blkdev_dio, bio); + dio->is_sync = is_sync = is_sync_kiocb(iocb); + if (dio->is_sync) { + dio->waiter = current; + bio_get(bio); + } else { + dio->iocb = iocb; + } + + dio->size = 0; + dio->multi_bio = false; + dio->should_dirty = is_read && iter_is_iovec(iter); + + /* + * Don't plug for HIPRI/polled IO, as those should go straight + * to issue + */ + if (!is_poll) + blk_start_plug(&plug); + + for (;;) { + bio_set_dev(bio, bdev); + bio->bi_iter.bi_sector = pos >> 9; + bio->bi_write_hint = iocb->ki_hint; + bio->bi_private = dio; + bio->bi_end_io = blkdev_bio_end_io; + bio->bi_ioprio = iocb->ki_ioprio; + + ret = bio_iov_iter_get_pages(bio, iter); + if (unlikely(ret)) { + bio->bi_status = BLK_STS_IOERR; + bio_endio(bio); + break; + } + + if (is_read) { + bio->bi_opf = REQ_OP_READ; + if (dio->should_dirty) + bio_set_pages_dirty(bio); + } else { + bio->bi_opf = dio_bio_write_op(iocb); + task_io_account_write(bio->bi_iter.bi_size); + } + if (iocb->ki_flags & IOCB_NOWAIT) + bio->bi_opf |= REQ_NOWAIT; + + dio->size += bio->bi_iter.bi_size; + pos += bio->bi_iter.bi_size; + + nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS); + if (!nr_pages) { + bool polled = false; + + if (iocb->ki_flags & IOCB_HIPRI) { + bio_set_polled(bio, iocb); + polled = true; + } + + qc = submit_bio(bio); + + if (polled) + WRITE_ONCE(iocb->ki_cookie, qc); + break; + } + + if (!dio->multi_bio) { + /* + * AIO needs an extra reference to ensure the dio + * structure which is embedded into the first bio + * stays around. + */ + if (!is_sync) + bio_get(bio); + dio->multi_bio = true; + atomic_set(&dio->ref, 2); + } else { + atomic_inc(&dio->ref); + } + + submit_bio(bio); + bio = bio_alloc(GFP_KERNEL, nr_pages); + } + + if (!is_poll) + blk_finish_plug(&plug); + + if (!is_sync) + return -EIOCBQUEUED; + + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (!READ_ONCE(dio->waiter)) + break; + + if (!(iocb->ki_flags & IOCB_HIPRI) || + !blk_poll(bdev_get_queue(bdev), qc, true)) + blk_io_schedule(); + } + __set_current_state(TASK_RUNNING); + + if (!ret) + ret = blk_status_to_errno(dio->bio.bi_status); + if (likely(!ret)) + ret = dio->size; + + bio_put(&dio->bio); + return ret; +} + +static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +{ + unsigned int nr_pages; + + if (!iov_iter_count(iter)) + return 0; + + nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1); + if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS) + return __blkdev_direct_IO_simple(iocb, iter, nr_pages); + + return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages)); +} + +static int blkdev_writepage(struct page *page, struct writeback_control *wbc) +{ + return block_write_full_page(page, blkdev_get_block, wbc); +} + +static int blkdev_readpage(struct file * file, struct page * page) +{ + return block_read_full_page(page, blkdev_get_block); +} + +static void blkdev_readahead(struct readahead_control *rac) +{ + mpage_readahead(rac, blkdev_get_block); +} + +static int blkdev_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, struct page **pagep, + void **fsdata) +{ + return block_write_begin(mapping, pos, len, flags, pagep, + blkdev_get_block); +} + +static int blkdev_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, struct page *page, + void *fsdata) +{ + int ret; + ret = block_write_end(file, mapping, pos, len, copied, page, fsdata); + + unlock_page(page); + put_page(page); + + return ret; +} + +static int blkdev_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + return generic_writepages(mapping, wbc); +} + +const struct address_space_operations def_blk_aops = { + .set_page_dirty = __set_page_dirty_buffers, + .readpage = blkdev_readpage, + .readahead = blkdev_readahead, + .writepage = blkdev_writepage, + .write_begin = blkdev_write_begin, + .write_end = blkdev_write_end, + .writepages = blkdev_writepages, + .direct_IO = blkdev_direct_IO, + .migratepage = buffer_migrate_page_norefs, + .is_dirty_writeback = buffer_check_dirty_writeback, +}; + +/* + * for a block special file file_inode(file)->i_size is zero + * so we compute the size by hand (just as in block_read/write above) + */ +static loff_t blkdev_llseek(struct file *file, loff_t offset, int whence) +{ + struct inode *bd_inode = bdev_file_inode(file); + loff_t retval; + + inode_lock(bd_inode); + retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode)); + inode_unlock(bd_inode); + return retval; +} + +static int blkdev_fsync(struct file *filp, loff_t start, loff_t end, + int datasync) +{ + struct inode *bd_inode = bdev_file_inode(filp); + struct block_device *bdev = I_BDEV(bd_inode); + int error; + + error = file_write_and_wait_range(filp, start, end); + if (error) + return error; + + /* + * There is no need to serialise calls to blkdev_issue_flush with + * i_mutex and doing so causes performance issues with concurrent + * O_SYNC writers to a block device. + */ + error = blkdev_issue_flush(bdev); + if (error == -EOPNOTSUPP) + error = 0; + + return error; +} + +static int blkdev_open(struct inode *inode, struct file *filp) +{ + struct block_device *bdev; + + /* + * Preserve backwards compatibility and allow large file access + * even if userspace doesn't ask for it explicitly. Some mkfs + * binary needs it. We might want to drop this workaround + * during an unstable branch. + */ + filp->f_flags |= O_LARGEFILE; + filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC; + + if (filp->f_flags & O_NDELAY) + filp->f_mode |= FMODE_NDELAY; + if (filp->f_flags & O_EXCL) + filp->f_mode |= FMODE_EXCL; + if ((filp->f_flags & O_ACCMODE) == 3) + filp->f_mode |= FMODE_WRITE_IOCTL; + + bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp); + if (IS_ERR(bdev)) + return PTR_ERR(bdev); + filp->f_mapping = bdev->bd_inode->i_mapping; + filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); + return 0; +} + +static int blkdev_close(struct inode *inode, struct file *filp) +{ + struct block_device *bdev = I_BDEV(bdev_file_inode(filp)); + + blkdev_put(bdev, filp->f_mode); + return 0; +} + +static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) +{ + struct block_device *bdev = I_BDEV(bdev_file_inode(file)); + fmode_t mode = file->f_mode; + + /* + * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have + * to updated it before every ioctl. + */ + if (file->f_flags & O_NDELAY) + mode |= FMODE_NDELAY; + else + mode &= ~FMODE_NDELAY; + + return blkdev_ioctl(bdev, mode, cmd, arg); +} + +/* + * Write data to the block device. Only intended for the block device itself + * and the raw driver which basically is a fake block device. + * + * Does not take i_mutex for the write and thus is not for general purpose + * use. + */ +static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *bd_inode = bdev_file_inode(file); + loff_t size = i_size_read(bd_inode); + struct blk_plug plug; + size_t shorted = 0; + ssize_t ret; + + if (bdev_read_only(I_BDEV(bd_inode))) + return -EPERM; + + if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev)) + return -ETXTBSY; + + if (!iov_iter_count(from)) + return 0; + + if (iocb->ki_pos >= size) + return -ENOSPC; + + if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT) + return -EOPNOTSUPP; + + size -= iocb->ki_pos; + if (iov_iter_count(from) > size) { + shorted = iov_iter_count(from) - size; + iov_iter_truncate(from, size); + } + + blk_start_plug(&plug); + ret = __generic_file_write_iter(iocb, from); + if (ret > 0) + ret = generic_write_sync(iocb, ret); + iov_iter_reexpand(from, iov_iter_count(from) + shorted); + blk_finish_plug(&plug); + return ret; +} + +static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct file *file = iocb->ki_filp; + struct inode *bd_inode = bdev_file_inode(file); + loff_t size = i_size_read(bd_inode); + loff_t pos = iocb->ki_pos; + size_t shorted = 0; + ssize_t ret; + + if (pos >= size) + return 0; + + size -= pos; + if (iov_iter_count(to) > size) { + shorted = iov_iter_count(to) - size; + iov_iter_truncate(to, size); + } + + ret = generic_file_read_iter(iocb, to); + iov_iter_reexpand(to, iov_iter_count(to) + shorted); + return ret; +} + +#define BLKDEV_FALLOC_FL_SUPPORTED \ + (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ + FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE) + +static long blkdev_fallocate(struct file *file, int mode, loff_t start, + loff_t len) +{ + struct inode *inode = bdev_file_inode(file); + struct block_device *bdev = I_BDEV(inode); + loff_t end = start + len - 1; + loff_t isize; + int error; + + /* Fail if we don't recognize the flags. */ + if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED) + return -EOPNOTSUPP; + + /* Don't go off the end of the device. */ + isize = i_size_read(bdev->bd_inode); + if (start >= isize) + return -EINVAL; + if (end >= isize) { + if (mode & FALLOC_FL_KEEP_SIZE) { + len = isize - start; + end = start + len - 1; + } else + return -EINVAL; + } + + /* + * Don't allow IO that isn't aligned to logical block size. + */ + if ((start | len) & (bdev_logical_block_size(bdev) - 1)) + return -EINVAL; + + filemap_invalidate_lock(inode->i_mapping); + + /* Invalidate the page cache, including dirty pages. */ + error = truncate_bdev_range(bdev, file->f_mode, start, end); + if (error) + goto fail; + + switch (mode) { + case FALLOC_FL_ZERO_RANGE: + case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: + error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, + GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); + break; + case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: + error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, + GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK); + break; + case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: + error = blkdev_issue_discard(bdev, start >> 9, len >> 9, + GFP_KERNEL, 0); + break; + default: + error = -EOPNOTSUPP; + } + + fail: + filemap_invalidate_unlock(inode->i_mapping); + return error; +} + +const struct file_operations def_blk_fops = { + .open = blkdev_open, + .release = blkdev_close, + .llseek = blkdev_llseek, + .read_iter = blkdev_read_iter, + .write_iter = blkdev_write_iter, + .iopoll = blkdev_iopoll, + .mmap = generic_file_mmap, + .fsync = blkdev_fsync, + .unlocked_ioctl = block_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = compat_blkdev_ioctl, +#endif + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .fallocate = blkdev_fallocate, +}; + +static __init int blkdev_init(void) +{ + return bioset_init(&blkdev_dio_pool, 4, + offsetof(struct blkdev_dio, bio), + BIOSET_NEED_BVECS|BIOSET_PERCPU_CACHE); +} +module_init(blkdev_init); diff --git a/block/genhd.c b/block/genhd.c index 567549a011d1..ab12ae6e636e 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -26,6 +26,7 @@ #include <linux/badblocks.h> #include "blk.h" +#include "blk-rq-qos.h" static struct kobject *block_depr; @@ -183,6 +184,7 @@ static struct blk_major_name { void (*probe)(dev_t devt); } *major_names[BLKDEV_MAJOR_HASH_SIZE]; static DEFINE_MUTEX(major_names_lock); +static DEFINE_SPINLOCK(major_names_spinlock); /* index in the above - for now: assume no multimajor ranges */ static inline int major_to_index(unsigned major) @@ -195,11 +197,11 @@ void blkdev_show(struct seq_file *seqf, off_t offset) { struct blk_major_name *dp; - mutex_lock(&major_names_lock); + spin_lock(&major_names_spinlock); for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next) if (dp->major == offset) seq_printf(seqf, "%3d %s\n", dp->major, dp->name); - mutex_unlock(&major_names_lock); + spin_unlock(&major_names_spinlock); } #endif /* CONFIG_PROC_FS */ @@ -271,6 +273,7 @@ int __register_blkdev(unsigned int major, const char *name, p->next = NULL; index = major_to_index(major); + spin_lock(&major_names_spinlock); for (n = &major_names[index]; *n; n = &(*n)->next) { if ((*n)->major == major) break; @@ -279,6 +282,7 @@ int __register_blkdev(unsigned int major, const char *name, *n = p; else ret = -EBUSY; + spin_unlock(&major_names_spinlock); if (ret < 0) { printk("register_blkdev: cannot get major %u for %s\n", @@ -298,6 +302,7 @@ void unregister_blkdev(unsigned int major, const char *name) int index = major_to_index(major); mutex_lock(&major_names_lock); + spin_lock(&major_names_spinlock); for (n = &major_names[index]; *n; n = &(*n)->next) if ((*n)->major == major) break; @@ -307,6 +312,7 @@ void unregister_blkdev(unsigned int major, const char *name) p = *n; *n = p->next; } + spin_unlock(&major_names_spinlock); mutex_unlock(&major_names_lock); kfree(p); } @@ -554,6 +560,8 @@ EXPORT_SYMBOL(device_add_disk); */ void del_gendisk(struct gendisk *disk) { + struct request_queue *q = disk->queue; + might_sleep(); if (WARN_ON_ONCE(!disk_live(disk) && !(disk->flags & GENHD_FL_HIDDEN))) @@ -570,8 +578,17 @@ void del_gendisk(struct gendisk *disk) fsync_bdev(disk->part0); __invalidate_device(disk->part0, true); + /* + * Fail any new I/O. + */ + set_bit(GD_DEAD, &disk->state); set_capacity(disk, 0); + /* + * Prevent new I/O from crossing bio_queue_enter(). + */ + blk_queue_start_drain(q); + if (!(disk->flags & GENHD_FL_HIDDEN)) { sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); @@ -593,6 +610,18 @@ void del_gendisk(struct gendisk *disk) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); + + blk_mq_freeze_queue_wait(q); + + rq_qos_exit(q); + blk_sync_queue(q); + blk_flush_integrity(); + /* + * Allow using passthrough request again after the queue is torn down. + */ + blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q); + __blk_mq_unfreeze_queue(q, true); + } EXPORT_SYMBOL(del_gendisk); @@ -1051,6 +1080,7 @@ static void disk_release(struct device *dev) struct gendisk *disk = dev_to_disk(dev); might_sleep(); + WARN_ON_ONCE(disk_live(disk)); disk_release_events(disk); kfree(disk->random); @@ -1263,6 +1293,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, out_destroy_part_tbl: xa_destroy(&disk->part_tbl); + disk->part0->bd_disk = NULL; iput(disk->part0->bd_inode); out_free_bdi: bdi_put(disk->bdi); diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 15a8be57203d..a0ffbabfac2c 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -151,6 +151,7 @@ struct kyber_ctx_queue { struct kyber_queue_data { struct request_queue *q; + dev_t dev; /* * Each scheduling domain has a limited number of in-flight requests @@ -257,7 +258,7 @@ static int calculate_percentile(struct kyber_queue_data *kqd, } memset(buckets, 0, sizeof(kqd->latency_buckets[sched_domain][type])); - trace_kyber_latency(kqd->q, kyber_domain_names[sched_domain], + trace_kyber_latency(kqd->dev, kyber_domain_names[sched_domain], kyber_latency_type_names[type], percentile, bucket + 1, 1 << KYBER_LATENCY_SHIFT, samples); @@ -270,7 +271,7 @@ static void kyber_resize_domain(struct kyber_queue_data *kqd, depth = clamp(depth, 1U, kyber_depth[sched_domain]); if (depth != kqd->domain_tokens[sched_domain].sb.depth) { sbitmap_queue_resize(&kqd->domain_tokens[sched_domain], depth); - trace_kyber_adjust(kqd->q, kyber_domain_names[sched_domain], + trace_kyber_adjust(kqd->dev, kyber_domain_names[sched_domain], depth); } } @@ -366,6 +367,7 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q) goto err; kqd->q = q; + kqd->dev = disk_devt(q->disk); kqd->cpu_latency = alloc_percpu_gfp(struct kyber_cpu_latency, GFP_KERNEL | __GFP_ZERO); @@ -774,7 +776,7 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd, list_del_init(&rq->queuelist); return rq; } else { - trace_kyber_throttled(kqd->q, + trace_kyber_throttled(kqd->dev, kyber_domain_names[khd->cur_domain]); } } else if (sbitmap_any_bit_set(&khd->kcq_map[khd->cur_domain])) { @@ -787,7 +789,7 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd, list_del_init(&rq->queuelist); return rq; } else { - trace_kyber_throttled(kqd->q, + trace_kyber_throttled(kqd->dev, kyber_domain_names[khd->cur_domain]); } } diff --git a/block/partitions/core.c b/block/partitions/core.c index 58c4c362c94f..7bea19dd9458 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -423,6 +423,7 @@ out_del: device_del(pdev); out_put: put_device(pdev); + return ERR_PTR(err); out_put_disk: put_disk(disk); return ERR_PTR(err); |